Bioinformatics and Medical Applications. Группа авторов
Читать онлайн книгу.
Chapter 4, “Deep Learning in Gait Abnormality Detection: Principles and Illustrations,” discusses cerebral palsy, a medical condition which is marked by weakened muscle coordination and other dysfunctions. This chapter proposes a deep learning technique, including support vector machines, multilayer perceptron, vanilla long short-term memory, and bi-directional LSTM, to diagnose cerebral palsy gait.
– Chapter 5, “Broad Applications of Network Embeddings in Computational Biology, Genomics, Medicine, and Health,” mainly focuses on the current traditional development of network or graph embedding and its application in computational biology, genomics, and healthcare. As biological networks are very complex and hard to interpret, a significant amount of progress is being made towards a graph or network embedding paradigm that can be used for visualization, representation, interpretation, and their correlation. Finally, to gain more biological insight, further quantification and evaluation of the network embedding technique and the key challenges are addressed.
– Chapter 6, “Heart Disease Classification Using Regional Wall Thickness by Ensemble Classifier,” focuses on the cardiac magnetic resonance images that are formed using radio waves and an influential magnetic field to produce images showing detailed structure within and around the heart. These images can be used to identify cardiac disease through various learning techniques employed to evaluate the heart’s anatomy and function in patients. In this chapter, an ensemble classification model is used to classify the type of heart disease.
– Chapter 7, “Deep Learning for Medical Informatics and Public Health,” highlights deep learning drawbacks related to data (higher number of features, dissimilar data, reliance on time, unsupervised data, etc.) and model (dependability, understandability, likelihood, scalability) for real-world applications. It emphasizes the DL techniques applied in medical informatics and recent public health case studies related to the application of deep learning and certain critical research questions.
– Chapter 8, “An Insight into Human Pose Estimation and Its Applications,” discusses human pose estimation and examines potential deep learning algorithms in great detail, as well as the benchmarking datasets. Recent important deep learning-based models are also investigated.
– Chapter 9, “Brain Tumor Analysis Using Deep Learning: Sensor and IoT-Based Approach for Futuristic Healthcare,” proposes an approach for the prediction of brain tumors.
– Chapter 10, “Study of Emission from Medicinal Woods to Curb Threats of Pollution and Diseases: Global Healthcare Paradigm Shift in the 21st Century,” focuses on techniques to prevent pollution-related diseases.
– Chapter 11, “An Economical Machine Learning Approach for Anomaly Detection in IoT Environment,” presents an improved version of the previous machine learning architecture for ransomware assault in the IoT since it could be more destructive and hence might influence the entire security administration scenario. Therefore, precautions are to be taken to secure the devices as well as data that is being transmitted among themselves, and threats have to be detected at an earlier stage to ensure complete security of the communication. The work proposed in this chapter analyzes the communicating data between these devices and aids in choosing an economically appropriate measure to secure the system.
– Chapter 12, “Indian Science of Yajna and Mantra to Cure Different Diseases: An Analysis Amidst Pandemic with a Simulated Approach,” discusses deep Yagya training, which is an amazingly practical application that is easy to use and exciting, and has a great impact on delicate thinking and emotions.
– Chapter 13, “Collection and Analysis of Big Data from Emerging Technologies in Healthcare,” discusses the fact that new diseases, such as COVID-19, are constantly being discovered. Since this results in a tremendous surge in data being generated and a huge burden falling on medical personnel, this is an area in which automation and emerging technologies can contribute significantly. Since combining big data with emerging healthcare technologies is the need of the hour, this chapter focuses on the collection of big data using emerging technologies like radio frequency identification (RFID), wireless sensor networks (WSN), and the internet of things (IoT), and their applications in the medical field. After discussing different data analysis approaches, the challenges and issues that arise during data analysis are explored and current research trends in the field are summarized.
– Chapter 14, “A Complete Overview of Sign Language Recognition and Translation Systems,” discusses the use of human body pose and hand pose estimation. Sign language recognition has been conventionally performed by some preliminary sensors and later evolved to various advanced deep learning-based computer vision systems. This chapter deals with the past, present, and future of sign language recognition systems. Sign language translation is also briefly discussed, providing insights into the natural language processing techniques used to accurately convert sign language to translated sentences.
The editors thank the contributors most profoundly for their time and effort.
A. SureshS. VimalY. Harold RobinsonDhinesh Kumar RamaswamiR. Udendhran February 2022
1
Probabilistic Optimization of Machine Learning Algorithms for Heart Disease Prediction
Jaspreet Kaur1*, Bharti Joshi2 and Rajashree Shedge2
1 Ramrao Adik Institute of Technology, Nerul, Navi Mumbai, India
2 Department of Computer Engineering Ramrao, Adik Institute of Technology Nerul, Navi Mumbai, India
Abstract
Big Data and Machine Learning have been effectively used in medical management leading to cost reduction in treatment, predicting the outbreak of epidemics, avoiding preventable diseases, and, improving the quality of life.
Prediction begins with the machine learning patterns from several existing known datasets and then applying something very similar to an obscure dataset to check the result. In this chapter, we investigate Ensemble Learning which overcomes the limitations of a single algorithm such as bias and variance by using a multitude of algorithms. The focus is not solely increasing the accuracy of weak classification algorithmic programs however additionally implementing the algorithm on a medical dataset wherever it is effectively used for analysis, prediction, and treatment. The consequence of the investigation indicates that ensemble techniques are powerful in improving the forecast accuracy and displaying an acceptable performance in disease prediction. Additionally, we have worked on a procedure to further improve the accuracy post applying ensemble method by focusing on the wrongly classified records and using probabilistic optimization to select pertinent columns by increasing their weight and doing a reclassification which would result in further improved accuracy. The accuracy hence achieved by our proposed method is, by far, quite competitive.
Keywords: Kaggle dataset, machine learning, probabilistic optimization, decision tree, random forest, Naive Bayes, K means, ensemble method, confusion matrix, probability, Euclidean distance
1.1